bidirectional_pci

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark readOnlyHint=true, and the description adds non-obvious context: proxy validity and completeness assumptions, failure modes for weak/invalid proxies, an evidence tier, and a minimum N warning. This goes well beyond the annotations and helps an agent anticipate poor identification.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is organized into focused sections (validation, assumptions, pre-conditions, failure modes, alternatives, N) with no repetition of schema fields or filler. The core identification is front-loaded and each section earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a complex estimator, it supplies assumptions, pre-conditions, failure modes, alternatives, evidence tier, and sample-size guidance, and an output schema exists so return details need not be repeated. The main gap is the missing explicit W/Z role mapping and a more precise contrast with the proximal/proximal_regression siblings.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds meaning to the proxy parameters by defining them as treatment-inducing and outcome-inducing negative controls relevant to the confounder and excluded from the causal channel. However, it never explicitly maps proxy_w to treatment-inducing and proxy_z to outcome-inducing, which prevents a higher score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific method ('Bidirectional proximal causal inference (Min, Zhang & Luo 2025)') and a precise action: solves both outcome and treatment bridges simultaneously in a two-way regression system. This distinguishes it from univariate proximal regression, select_pci_proxies, and DML even without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Pre-conditions state when the method is applicable (valid negative-control proxies, bridge function/completeness), failure modes say what to do if assumptions fail, and the Alternatives line points to sp.select_pci_proxies and sp.dml. It lacks an explicit 'use X instead when Y' contrast, so it is not a full 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.